© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73171
    Prev
    Next
    INDEX
    Explanations

    (i.e

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -2.36
    y
    -2.02
    も
    -1.97
    が
    -1.91
     frågan
    -1.87
     on
    -1.83
    in
    -1.83
    を
    -1.82
    p
    -1.80
    a
    -1.79
    POSITIVE LOGITS
    為に
    2.25
     miniaturka
    2.14
    の絵
    2.09
    aceite
    2.06
    感じで
    2.02
    𖣔
    2.00
    ができます
    1.94
    麃
    1.93
    にします
    1.88
    ごとの
    1.87
    Activations Density 0.030%

    No Known Activations